© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 15622
    Prev
    Next
    INDEX
    Explanations

    terms related to combustion processes and energy generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oad
    -0.08
    ying
    -0.07
     Roh
    -0.07
    isman
    -0.07
    yl
    -0.06
    ws
    -0.06
    amen
    -0.06
    ych
    -0.06
    oint
    -0.06
    acey
    -0.06
    POSITIVE LOGITS
    reesome
    0.08
    IBLE
    0.07
    orrow
    0.07
     Ign
    0.07
    querque
    0.07
     Globe
    0.07
    leigh
    0.07
    erras
    0.07
     engine
    0.07
     IGN
    0.07
    Activations Density 0.003%

    No Known Activations